Lewati ke konten
TakoAPI
Kembali ke skill

percept-ambient

oleh jarvis563

AI & LLMs
338Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Ambient intelligence mode — continuous context awareness without explicit commands.

Deskripsi

Apa yang Dilakukan Skill Ini

Runs continuously in the background, capturing ambient conversations and building a local knowledge graph of people, projects, and relationships. When an agent needs context, it assembles a structured Context Packet from accumulated history — no explicit commands required. All data is stored locally with configurable retention and privacy controls.

Passive accumulation means agents have situational awareness without users manually logging notes or issuing commands.

Kapan Menggunakannya

  • Recalling who was involved in a past project decision
  • Answering 'what do you know about this person?' without manual notes
  • Giving an agent background context before starting a task
  • Tracking which projects are active across daily conversations
  • Searching conversation history semantically for a specific topic

Contoh Alur Kerja

INPUT

User asks: What do you know about the Johnson account?

AGENT
  1. 1

    Receives natural-language query

  2. 2

    Runs hybrid FTS5 and vector search over stored utterances

  3. 3

    Resolves entities and relationships linked to 'Johnson account'

  4. 4

    Assembles a Context Packet with recent conversations, entity data, and relationship mappings

  5. 5

    Returns structured context to the requesting agent

OUTPUT

Context Packet containing recent conversations mentioning the Johnson account, resolved entity records, and mapped relationships

Instalasi

clawhub install jarvis563/percept-ambient

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan